基于ADAS联网时空数据的路段交通参数估算模型

马天奕; 文家强; 王丽园; 吕能超; 王玉刚

doi:10.3963/j.jssn.1674-4861.2021.01.008

基于ADAS联网时空数据的路段交通参数估算模型

doi: 10.3963/j.jssn.1674-4861.2021.01.008

马天奕^1,,
文家强^{2, 3},
王丽园¹,
吕能超^{2, 3, ,},
王玉刚^{2, 3}

1.
中交第二公路勘察设计研究院有限公司武汉 430056
2.
武汉理工大学智能交通系统研究中心武汉 430063
3.
武汉理工大学水路公路交通安全控制与装备教育部工程研究中心武汉 430063

基金项目:

国家自然科学基金项目 51775396

国家自然科学基金项目 52072290

湖北省杰出青年基金 2020CFA081

中央高校基本科研业务费专项基金 191044003

中交集团科技研发项目 2019-ZJKJ-ZDZX02

详细信息

作者简介:
马天奕（1994—），助理工程师.研究方向：智慧交通.E-mail：matianyi0316@163.com

通讯作者:
吕能超（1982—），博士，教授.研究方向：交通安全.E-mail：lnc@whut.edu.cn

中图分类号: U491.2
计量
- 文章访问数: 295
- HTML全文浏览量: 200
- PDF下载量: 12
- 被引次数: 0
出版历程
- 收稿日期: 2020-11-26
- 刊出日期: 2021-02-28

An Estimation Model of Section Traffic Parameters Based on Connected ADAS Spatiotemporal Data

MA Tianyi^1
,,
WEN Jiaqiang^{2, 3},
WANG Liyuan¹,
LYU Nengchao^{2, 3
, ,},
WANG Yugang^{2, 3}

1.
Second Highway Consultant Company LTD., CCCC, Wuhan 430056, China
2.
Intelligent Transportation Systems Research Center, Wuhan University of Technology, Wuhan 430063, China
3.
Engineering Research Center for Transportation Safety of Ministry of Education, Wuhan University of Technology, Wuhan 430063, China

摘要

摘要: 交通参数实时获取是道路交通管控的重要基础。针对固定检测器观测范围受限和浮动车数量需求大的问题，研究了1种利用车载ADAS联网数据进行路段交通参数估算的方法。通过分析车载ADAS感知的前向目标参数与交通参数的关系，结合广义交通量定义，并考虑多车道条件下ADAS车辆及其邻近前车的相对运动变化特性，建立了1种非稳态交通条件下的交通参数估算模型。在仿真实验环境下获得定参数据集和验证数据集，完成对模型的参数标定和验证，并探讨时空分辨率和ADAS车辆渗透率对模型估算精度的影响规律。基于实验数据分析，结果表明，时间分辨率降低5 min，所提模型估算误差平均减小3.4%，降低时间分辨率可以提升所提模型的估算精度；空间分辨率降低500 m，流量和密度的估算误差平均减小1.68%，却可能导致速度估算误差平均增加5.19%；ADAS车辆渗透率的增长可以增强估算交通参数和观测交通参数在路段时空区域的契合程度。在ADAS逐渐装车应用的背景下，所提的交通参数估算模型可快速、精准获取路段连续时空范围内的交通量信息。
- 交通工程 /
- 交通参数 /
- 估算模型 /
- ADAS /
- 时空分辨率 /
- 渗透率
Abstract: Real-time acquisition of traffic parameters is an essential basis for road traffic control. A method for estimating section traffic parameters using the connected ADAS data is studied for the limited observation range of fixed detectors and the great demand for floating vehicles. A traffic parameter-estimation model under unsteady traffic conditions is established by analyzing the relationship between forward target parameters perceived by on-board ADAS and traffic parameters, the definition of generalized traffic volume, and the relative motion characteristics of the ADAS vehicle and its neighboring vehicle in a multi-lane environment. According to the simulation, the calibration data set and the verification data set are obtained to complete the parameter calibration and verification of the model. Also, the paper discusses the influences of time and space resolutions, and ADAS vehicle penetration rates on the estimation accuracy of the model. The analysis shows that when the time resolution is reduced by 5 min, the estimation error is reduced by 3.4% on average; reducing the time resolution can improve the estimation accuracy of the proposed model. When the space resolution is reduced by 500 m, the estimation error of flow and density is reduced by 1.68% on average; however, it may lead to an average increase of 5.19% in speed estimation error. The increased penetration rate of ADAS vehicles can enhance the overall fit between estimated traffic parameters and observed traffic parameters in the time-space area of the road sections. In the context of the gradual application of ADAS, the proposed model of traffic parameter estimation can quickly obtain the traffic volume information in the continuous time-space range of the road sections.
- traffic engineering /
- traffic parameter /
- estimation model /
- ADAS /
- time-space resolution /
- penetration rate

HTML全文

图 1 车载ADAS所检测的前方目标示意图

Figure 1. Front target detected by the on-board ADAS

下载: 全尺寸图片幻灯片

图 2 不同交通条件下的车辆状态变化

Figure 2. Changes of the vehicle status in different traffic conditions

下载: 全尺寸图片幻灯片

图 3 车辆行驶轨迹与时空面积|S_{i, A}|的示意图

Figure 3. Vehicle trajectory and time-space area |S_{i, A}|

下载: 全尺寸图片幻灯片

图 4 实验场景示意图

Figure 4. Experiment scene

下载: 全尺寸图片幻灯片

图 5 数据处理和运用流程

Figure 5. Data processing and application process

下载: 全尺寸图片幻灯片

图 6 修正系数f值的统计

Figure 6. Statistics of correction coefficient f value

下载: 全尺寸图片幻灯片

图 7 修正系数f值的正态分布曲线

Figure 7. Normal distribution curve of correction coefficient f value

下载: 全尺寸图片幻灯片

图 8 估算交通参数和观测交通参数的时空分布图

Figure 8. Time-space distribution of estimated traffic parameters and observed traffic parameters

下载: 全尺寸图片幻灯片

图 9 流量估算效果比较

Figure 9. Comparison of flow estimation performance

下载: 全尺寸图片幻灯片

图 10 密度估算效果比较

Figure 10. Comparison of density estimation performance

下载: 全尺寸图片幻灯片

图 11 速度估算效果比较

Figure 11. Comparison of speed estimation performance

下载: 全尺寸图片幻灯片

表 1 DHW与K和THW与Q数学概念分析

Table 1. Analysis of mathematical concepts of DHW and K, THW and Q

变量	定义	分析
DHW	单个车辆所占据的路段长度（m/veh)	存在概念相关性
K	单位长度内所拥有的车辆数量/(veh/km)	存在概念相关性
THW	单个车辆达到某断面所需要的时间/(s/veh)	存在概念相关性
Q	单位时间内通过某断面的车辆数量/(veh/h)	存在概念相关性

下载: 导出CSV

表 2 时空分辨率组别设定

Table 2. Time-space resolution group setting

组别	时间分辨率/min	空间分辨率/m	渗透率	时空区域矩阵
①	5	500	3, 5, 7, 10, 15	8×12
②	5	1 000	3, 5, 7, 10, 15	4×12
③	10	500	3, 5, 7, 10, 15	8×6
④	10	1 000	3, 5, 7, 10, 15	4×6
⑤	15	500	3, 5, 7, 10, 15	8×4
⑥	15	1 000	3, 5, 7, 10, 15	4×4

下载: 导出CSV

表 3 不同时空分辨率下的修正系数f

Table 3. Correction coefficient f under different time-space resolutions

序号	时间分辨率/min	空间分辨率/m	修正系数f值
1	5	500	2.45
2	5	1 000	4.34
3	10	500	2.50
4	10	1 000	4.56
5	15	500	2.63
6	15	1 000	4.45

下载: 导出CSV

表 4 不同条件下的交通量估计比较

Table 4. Comparison of traffic-parameter estimation under different conditions

时空分辨率	渗透率/%	流量		密度		速度
时空分辨率	渗透率/%	RMSPE /%	EC	RMSP /%	EC	RMSP /%	EC
	15	17.67	0.992 4	17.87	0.990 4	4.59	0.999 5
	10	22.65	0.989 3	19.70	0.989 4	6.03	0.999 1
5 minx500 m	7	25.32	0.985 1	23.81	0.983 4	7.84	0.998 5
	5	25.92	0.982 9	26.73	0.977 8	8.17	0.998 4
	3	32.40	0.974 8	28.73	0.974 4	14.27	0.994 7
	15	16.22	0.992 1	17.77	0.992 6	9.04	0.998 1
	10	20.81	0.987 0	19.08	0.990 6	9.31	0.998 0
5 minx1 000 m	7	22.44	0.985 7	19.24	0.990 0	13.41	0.995 9
	5	29.07	0.972 0	28.21	0.977 6	17.93	0.992 9
	3	28.49	0.974 1	28.90	0.979 5	17.16	0.993 4
	15	15.67	0.993 1	16.05	0.993 8	4.20	0.999 6
	10	16.88	0.993 7	14.54	0.995 2	4.95	0.999 4
10 minx500 m	7	17.85	0.991 2	17.59	0.991 7	5.25	0.999 3
	5	19.16	0.989 3	18.03	0.990 6	5.08	0.999 4
	3	25.68	0.982 8	23.85	0.985 1	6.92	0.998 9
	15	14.82	0.994 1	14.56	0.995 3	8.77	0.998 2
	10	17.82	0.992 0	14.87	0.994 7	8.45	0.998 4
10 minx1 000 m	7	17.67	0.992 6	15.90	0.994 1	10.04	0.997 7
	5	20.33	0.989 0	16.94	0.993 4	12.69	0.996 4
	3	22.67	0.986 9	21.29	0.990 7	12.46	0.996 4
	15	14.59	0.994 7	14.63	0.995 7	3.60	0.999 7
	10	14.05	0.995 9	14.86	0.995 6	4.32	0.999 6
15 minx500 m	7	13.07	0.995 5	11.78	0.997 0	4.32	0.999 6
	5	17.52	0.990 8	15.65	0.994 0	4.75	0.999 5
	3	18.56	0.989 5	15.71	0.993 5	6.22	0.999 1
	15	13.64	0.995 9	14.44	0.994 9	7.85	0.998 6
	10	11.98	0.996 7	12.86	0.995 6	8.07	0.998 5
15 minx1 000 m	7	12.60	0.996 7	12.53	0.995 9	9.41	0.998 0
	5	18.68	0.989 9	19.58	0.988 4	12.71	0.996 4
	3	19.02	0.991 5	16.51	0.992 2	11.01	0.997 2

下载: 导出CSV

参考文献(30)

[1]	GEROLIMINIS N, DAGANZO C F. Existence of urban-scale macroscopic fundamental diagrams: Some experimental findings[J]. Transportation Research Part B: Methodological, 2008, 42(9): 759-770. doi: 10.1016/j.trb.2008.02.002
[2]	张亮亮, 贾元华, 牛忠海, 等. 交通状态划分的参数权重聚类方法研究[J]. 交通运输系统工程与信息, 2014, 14(6): 147-151. doi: 10.3969/j.issn.1009-6744.2014.06.023 ZHANG Liangliang, JIA Yuanhua, NIU Zhonghai, et al. Traffic state classification based on parameter weighting and clustering method[J]. Journal of Transportation Systems Engineering and Information Technology, 2014, 14(6): 147-151. (in Chinese) doi: 10.3969/j.issn.1009-6744.2014.06.023
[3]	QU X, WANG S, ZHANG J. On the fundamental diagram for freeway traffic: A novel calibration approach for single-regime models[J]. Transportation Research Part B: Methodological, 2015(73): 91-102. http://www.sciencedirect.com/science/article/pii/S0191261515000041
[4]	DURET A, YUAN Y. Traffic state estimation based on Eulerian and Lagrangian observations in a mesoscopic modeling framework[J]. Transportation Research Part B: Methodological, 2017 (101): 51-71. http://www.sciencedirect.com/science/article/pii/S0191261516305240
[5]	SEO T, KUSAKABE T. Probe vehicle-based traffic state estimation method with spacing information and conservation law[J]. Transportation Research Part C: Emerging Technologies, 2015 (59): 391-403. http://www.sciencedirect.com/science/article/pii/S0968090X15002132
[6]	ALJAMAL M A, ABDELGHAFFAR H M, RAKHA H A. Realtime estimation of vehicle counts on signalized intersection approaches using probe vehicle data[J/OL].(2020-02)[2021- 01-22]. https://ieeexplore.ieee.org/document/9007043.
[7]	唐克双, 徐天祥, 董可然, 等. 基于低频定点检测数据的交叉口交通状态估计[J]. 同济大学学报(自然科学版), 2017, 45 (5): 705-713. https://www.cnki.com.cn/Article/CJFDTOTAL-TJDZ201705013.htm TANG Keshuang, XU Tianxiang, DONG Keran, et al. Traffic state estimation based on low frequency detection data at intersections[J]. Journal of Tongji University(Natural Science Edition), 2017, 45(5): 705-713. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TJDZ201705013.htm
[8]	SEO T, KUSAKABE T, ASAKURA Y. Estimation of flow and density using probe vehicles with spacing measurement equipment[J]. Transportation Research Part C: Emerging Technologies, 2015(53): 134-150. http://www.sciencedirect.com/science/article/pii/S0968090X15000443
[9]	SINGH K, LI B. Estimation of traffic densities for multilane roadways using a Markov model approach[J]. IEEE Transactions on Industrial Electronics, 2012, 59(11): 4369-4376. doi: 10.1109/TIE.2011.2180271
[10]	SEO T, BAYEN A M, KUSAKABE T, et al. Traffic state estimation on highway: a comprehensive survey[J]. Annual Reviews in Control, 2017(43): 128-151. http://smartsearch.nstl.gov.cn/paper_detail.html?id=b9166f0ad576da7a787b473f4b0383a7
[11]	陈喜群, 周凌霄, 曹震. 基于图卷积网络的路网短时交通流预测研究[J]. 交通运输系统工程与信息, 2020, 20(4): 49-55. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202004008.htm CHEN Xiqun, ZHOU Lingxiao, CAO Zhen. Short-term network-wide traffic prediction based on graph convolutional network[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(4): 49-55. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202004008.htm
[12]	HERRERA J C, WORK D B, HERRING R, et al. Evaluation of traffic data obtained via GPS-enabled mobile phones: the mobile century field experiment[J]. Transportation Research Part C: Emerging Technologies, 2010, 18(4): 568-583. doi: 10.1016/j.trc.2009.10.006
[13]	QIU T Z, LU X Y, CHOW A H F, et al. Estimation of freeway traffic density with loop detector and probe vehicle data[J]. Transportation Research Record: Journal of the Transportation Research Board, 2010(2178): 21-29. http://www.researchgate.net/publication/277392609_Estimation_of_Freeway_Traffic_Density_with_Loop_Detector_and_Probe_Vehicle_Data
[14]	BHASKAR A, TSUBOTA T, KIEU L M, et al. Urban traffic state estimation: Fusing point and zone based data[J]. Transportation Research Part C: Emerging Technologies, 2014 (48): 120-142. http://www.sciencedirect.com/science/article/pii/S0968090X14002319
[15]	ZHANG J, HE S, WANG W, et al. Accuracy analysis of freeway traffic speed estimation based on the integration of cellular probe system and loop detectors[J]. Journal of Intelligent Transportation Systems, 2015, 19(4): 411-426. doi: 10.1080/15472450.2014.1000456
[16]	MONTERO L, PACHECO M, BARCELO J, et al. Case study on cooperative car data for estimating traffic states in an urban network[J]. Transportation Research Record: Journal of the Transportation Research Board, 2016(2594): 127-137. http://www.researchgate.net/publication/309517357_Case_Study_on_Cooperative_Car_Data_for_Estimating_Traffic_States_in_an_Urban_Network
[17]	YUAN Y, VAN LINT J W C, WILSON R E, et al. Real-time Lagrangian traffic state estimator for freeways[J]. IEEE Transactions on Intelligent Transportation Systems, 2012, 13(1): 59-70. doi: 10.1109/TITS.2011.2178837
[18]	林晓辉, 徐建闽. 基于自适应加权平均的路网MFD估测融合方法[J]. 交通运输系统工程与信息, 2018, 18(6): 102-109. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201806015.htm LIN Xiaohui, XU Jianmin. Macroscopic fundamental diagram estimation fusion method of road networks based on adaptive weighted average[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(6): 102-109. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT201806015.htm
[19]	李晨朋, 韩印, 王馨玉. 车联网环境下公交路径交通状态估计方法研究[J]. 交通运输研究, 2018, 4(5): 29-34. https://www.cnki.com.cn/Article/CJFDTOTAL-JTBH201805004.htm LI Chenpeng, HAN Yin, WANG Xinyu. Traffic state estimation method of bus route in connected vehicle environment[J]. Transport Research, 2018, 4(5): 29-34. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTBH201805004.htm
[20]	符旭, 欧梦宁, 闫旭普, 等. 基于分布式车辆速度检测信息的城市快速路交通状态估计[J]. 交通运输工程与信息学报, 2016, 14(4): 105-112. doi: 10.3969/j.issn.1672-4747.2016.04.017 FU Xu, OU Mengning, YAN Xupu, et al. Traffic state estimation of urban freeway traffic based on distributed speed detecting information networks[J]. Journal of Transportation Engineering and Information, 2016, 14(4): 105-112. (in Chinese) doi: 10.3969/j.issn.1672-4747.2016.04.017
[21]	HOU W, LYU N, LIU Z, et al. Modeling large vehicle operating speed characteristics on freeway alignment based on aggregated GPS data[J]. IET Intelligent Transport Systems, 2020, 14 (8): 857-865. doi: 10.1049/iet-its.2019.0563
[22]	SEO T, KUSAKABE T. Probe vehicle-based traffic flow estimation method without fundamental diagram[J]. Transportation Research Procedia, 2015(9): 149-163. http://www.sciencedirect.com/science/article/pii/s2352146515001696
[23]	GRUMERT E F, TAPANI A. Traffic state estimation using connected vehicles and stationary detectors[J/OL].(2018-01)[2021-01-22]. https://www.hindawi.com/journals/jat/2018/4106086/.
[24]	LYU N, DUAN Z, MA C, et al. Safety margins: A novel approach from risk homeostasis theory for evaluating the impact of advanced driver assistance systems on driving behavior in near-crash events[J]. Journal of Intelligent Transportation Systems, 2020, 25(1): 93-106.
[25]	BENGLER K, DIETMAYR K, FARBER B, et al. Three decades of driver assistance systems: Review and future perspectives[J]. IEEE Intelligent Transportation Systems Magazine, 2014, 6(4): 6-22. doi: 10.1109/MITS.2014.2336271
[26]	WILBY M R, DIAZ J J V, GONZALEZ A B R, et al. Lightweight occupancy estimation on freeways using extended floating car data[J]. Journal of Intelligent Transportation Systems, 2014, 18(2): 149-163. doi: 10.1080/15472450.2013.801711
[27]	刘永涛, 华珺, 赵俊玮, 等. 场景风险引导下驾驶人应激反应能力研究[J]. 交通信息与安全, 2019, 37(3): 35-41. https://www.cnki.com.cn/Article/CJFDTOTAL-JTJS201903005.htm LIU Yongtao, HUA Jun, ZHAO Junwei, et al. Emergency response ability of drivers under risk guidance situations[J]. Journal of Transport Information and Safety, 2019, 37(3): 35-41. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JTJS201903005.htm
[28]	王祺, 李力, 胡坚明, 等. 不同车头间距下交通流的速度分布[J]. 清华大学学报(自然科学版), 2011, 51(3): 309-312. https://www.cnki.com.cn/Article/CJFDTOTAL-QHXB201103004.htm WANG Qi, LI Li, HU Jianming, et al. Traffic velocity distributions for different spacings[J]. Journal of Tsinghua University (Science and Technology), 2011, 51(3): 309-312. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-QHXB201103004.htm
[29]	EDIE L C, FOOTE R S, HERMAN R, et al. Analysis of single lane traffic flow[J]. Traffic Engineering, 1962, 33(4): 21-27. http://www.researchgate.net/publication/284577535_Analysis_of_single_lane_traffic_flow
[30]	唐克双, 梅雨, 李克平. 基于浮动车数据的交通状态估计精度仿真评价[J]. 同济大学学报(自然科学版), 2014, 42(9): 1347-1351. https://www.cnki.com.cn/Article/CJFDTOTAL-TJDZ201409007.htm TANG Keshuang, MEI Yu, LI Keping. A simulation-based evaluation of traffic state estimation accuracy by using floating car data in complex road networks[J]. Journal of Tongji University(Natural Science Edition), 2014, 42(9): 1347-1351. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TJDZ201409007.htm